| Message ID | 160650039275.2890576.7191201185534571391.stgit@firesoul (mailing list archive) |
|---|---|
| State | Changes Requested |
| Delegated to: | BPF |
| Headers | show |
| Series | bpf: New approach for BPF MTU handling | expand |
| Context | Check | Description |
|---|---|---|
| netdev/cover_letter | success | Link |
| netdev/fixes_present | success | Link |
| netdev/patch_count | success | Link |
| netdev/tree_selection | success | Clearly marked for bpf-next |
| netdev/subject_prefix | success | Link |
| netdev/source_inline | success | Was 0 now: 0 |
| netdev/verify_signedoff | success | Link |
| netdev/module_param | success | Was 0 now: 0 |
| netdev/build_32bit | success | Errors and warnings before: 15753 this patch: 15753 |
| netdev/kdoc | success | Errors and warnings before: 0 this patch: 0 |
| netdev/verify_fixes | success | Link |
| netdev/checkpatch | success | total: 0 errors, 0 warnings, 0 checks, 126 lines checked |
| netdev/build_allmodconfig_warn | success | Errors and warnings before: 15665 this patch: 15665 |
| netdev/header_inline | success | Link |
| netdev/stable | success | Stable not CCed |
On 11/27/20 7:06 PM, Jesper Dangaard Brouer wrote: > The BPF-helpers for FIB lookup (bpf_xdp_fib_lookup and bpf_skb_fib_lookup) > can perform MTU check and return BPF_FIB_LKUP_RET_FRAG_NEEDED. The BPF-prog > don't know the MTU value that caused this rejection. > > If the BPF-prog wants to implement PMTU (Path MTU Discovery) (rfc1191) it > need to know this MTU value for the ICMP packet. > > Patch change lookup and result struct bpf_fib_lookup, to contain this MTU > value as output via a union with 'tot_len' as this is the value used for > the MTU lookup. > > V5: > - Fixed uninit value spotted by Dan Carpenter. > - Name struct output member mtu_result > > Reported-by: kernel test robot <lkp@intel.com> > Reported-by: Dan Carpenter <dan.carpenter@oracle.com> > Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> > --- > include/uapi/linux/bpf.h | 11 +++++++++-- > net/core/filter.c | 22 +++++++++++++++------- > tools/include/uapi/linux/bpf.h | 11 +++++++++-- > 3 files changed, 33 insertions(+), 11 deletions(-) > > diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h > index c3458ec1f30a..848398bd5a54 100644 > --- a/include/uapi/linux/bpf.h > +++ b/include/uapi/linux/bpf.h > @@ -2220,6 +2220,9 @@ union bpf_attr { > * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the > * packet is not forwarded or needs assist from full stack > * > + * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU > + * was exceeded and output params->mtu_result contains the MTU. > + * > * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) > * Description > * Add an entry to, or update a sockhash *map* referencing sockets. > @@ -4961,9 +4964,13 @@ struct bpf_fib_lookup { > __be16 sport; > __be16 dport; > > - /* total length of packet from network header - used for MTU check */ > - __u16 tot_len; > + union { /* used for MTU check */ > + /* input to lookup */ > + __u16 tot_len; /* L3 length from network hdr (iph->tot_len) */ > > + /* output: MTU value */ > + __u16 mtu_result; > + }; > /* input: L3 device index for lookup > * output: device index from FIB lookup > */ > diff --git a/net/core/filter.c b/net/core/filter.c > index 84d77c425fbe..25b137ffdced 100644 > --- a/net/core/filter.c > +++ b/net/core/filter.c > @@ -5265,12 +5265,14 @@ static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { > #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6) > static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, > const struct neighbour *neigh, > - const struct net_device *dev) > + const struct net_device *dev, u32 mtu) > { > memcpy(params->dmac, neigh->ha, ETH_ALEN); > memcpy(params->smac, dev->dev_addr, ETH_ALEN); > params->h_vlan_TCI = 0; > params->h_vlan_proto = 0; > + if (mtu) > + params->mtu_result = mtu; /* union with tot_len */ > > return 0; > } > @@ -5286,8 +5288,8 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, > struct net_device *dev; > struct fib_result res; > struct flowi4 fl4; > + u32 mtu = 0; > int err; > - u32 mtu; > > dev = dev_get_by_index_rcu(net, params->ifindex); > if (unlikely(!dev)) > @@ -5354,8 +5356,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, > > if (check_mtu) { > mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst); > - if (params->tot_len > mtu) > + if (params->tot_len > mtu) { > + params->mtu_result = mtu; /* union with tot_len */ > return BPF_FIB_LKUP_RET_FRAG_NEEDED; > + } > } > > nhc = res.nhc; > @@ -5389,7 +5393,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, > if (!neigh) > return BPF_FIB_LKUP_RET_NO_NEIGH; > > - return bpf_fib_set_fwd_params(params, neigh, dev); > + return bpf_fib_set_fwd_params(params, neigh, dev, mtu); > } > #endif > > @@ -5406,7 +5410,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, > struct flowi6 fl6; > int strict = 0; > int oif, err; > - u32 mtu; > + u32 mtu = 0; > > /* link local addresses are never forwarded */ > if (rt6_need_strict(dst) || rt6_need_strict(src)) > @@ -5481,8 +5485,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, > > if (check_mtu) { > mtu = ipv6_stub->ip6_mtu_from_fib6(&res, dst, src); > - if (params->tot_len > mtu) > + if (params->tot_len > mtu) { > + params->mtu_result = mtu; /* union with tot_len */ > return BPF_FIB_LKUP_RET_FRAG_NEEDED; And with mentioned approach from [0] we also only ever need to set the above, but we don't need to drag it anywhere else via bpf_fib_set_fwd_params() with the extra zero check on mtu. So this should simplify this one as well. [0] https://lore.kernel.org/bpf/6f9cac4e-a231-ff8d-43a5-828995ca5ec7@iogearbox.net/ > + } > } > > if (res.nh->fib_nh_lws) > @@ -5502,7 +5508,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, > if (!neigh) > return BPF_FIB_LKUP_RET_NO_NEIGH; > > - return bpf_fib_set_fwd_params(params, neigh, dev); > + return bpf_fib_set_fwd_params(params, neigh, dev, mtu);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c3458ec1f30a..848398bd5a54 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2220,6 +2220,9 @@ union bpf_attr { * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the * packet is not forwarded or needs assist from full stack * + * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU + * was exceeded and output params->mtu_result contains the MTU. + * * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) * Description * Add an entry to, or update a sockhash *map* referencing sockets. @@ -4961,9 +4964,13 @@ struct bpf_fib_lookup { __be16 sport; __be16 dport; - /* total length of packet from network header - used for MTU check */ - __u16 tot_len; + union { /* used for MTU check */ + /* input to lookup */ + __u16 tot_len; /* L3 length from network hdr (iph->tot_len) */ + /* output: MTU value */ + __u16 mtu_result; + }; /* input: L3 device index for lookup * output: device index from FIB lookup */ diff --git a/net/core/filter.c b/net/core/filter.c index 84d77c425fbe..25b137ffdced 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5265,12 +5265,14 @@ static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6) static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, const struct neighbour *neigh, - const struct net_device *dev) + const struct net_device *dev, u32 mtu) { memcpy(params->dmac, neigh->ha, ETH_ALEN); memcpy(params->smac, dev->dev_addr, ETH_ALEN); params->h_vlan_TCI = 0; params->h_vlan_proto = 0; + if (mtu) + params->mtu_result = mtu; /* union with tot_len */ return 0; } @@ -5286,8 +5288,8 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, struct net_device *dev; struct fib_result res; struct flowi4 fl4; + u32 mtu = 0; int err; - u32 mtu; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) @@ -5354,8 +5356,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (check_mtu) { mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst); - if (params->tot_len > mtu) + if (params->tot_len > mtu) { + params->mtu_result = mtu; /* union with tot_len */ return BPF_FIB_LKUP_RET_FRAG_NEEDED; + } } nhc = res.nhc; @@ -5389,7 +5393,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (!neigh) return BPF_FIB_LKUP_RET_NO_NEIGH; - return bpf_fib_set_fwd_params(params, neigh, dev); + return bpf_fib_set_fwd_params(params, neigh, dev, mtu); } #endif @@ -5406,7 +5410,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, struct flowi6 fl6; int strict = 0; int oif, err; - u32 mtu; + u32 mtu = 0; /* link local addresses are never forwarded */ if (rt6_need_strict(dst) || rt6_need_strict(src)) @@ -5481,8 +5485,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (check_mtu) { mtu = ipv6_stub->ip6_mtu_from_fib6(&res, dst, src); - if (params->tot_len > mtu) + if (params->tot_len > mtu) { + params->mtu_result = mtu; /* union with tot_len */ return BPF_FIB_LKUP_RET_FRAG_NEEDED; + } } if (res.nh->fib_nh_lws) @@ -5502,7 +5508,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (!neigh) return BPF_FIB_LKUP_RET_NO_NEIGH; - return bpf_fib_set_fwd_params(params, neigh, dev); + return bpf_fib_set_fwd_params(params, neigh, dev, mtu); } #endif @@ -5581,6 +5587,8 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, */ if (params->tot_len == 0 && !is_skb_forwardable(dev, skb)) rc = BPF_FIB_LKUP_RET_FRAG_NEEDED; + + params->mtu_result = dev->mtu; /* union with tot_len */ } return rc; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c3458ec1f30a..848398bd5a54 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2220,6 +2220,9 @@ union bpf_attr { * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the * packet is not forwarded or needs assist from full stack * + * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU + * was exceeded and output params->mtu_result contains the MTU. + * * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) * Description * Add an entry to, or update a sockhash *map* referencing sockets. @@ -4961,9 +4964,13 @@ struct bpf_fib_lookup { __be16 sport; __be16 dport; - /* total length of packet from network header - used for MTU check */ - __u16 tot_len; + union { /* used for MTU check */ + /* input to lookup */ + __u16 tot_len; /* L3 length from network hdr (iph->tot_len) */ + /* output: MTU value */ + __u16 mtu_result; + }; /* input: L3 device index for lookup * output: device index from FIB lookup */
The BPF-helpers for FIB lookup (bpf_xdp_fib_lookup and bpf_skb_fib_lookup) can perform MTU check and return BPF_FIB_LKUP_RET_FRAG_NEEDED. The BPF-prog don't know the MTU value that caused this rejection. If the BPF-prog wants to implement PMTU (Path MTU Discovery) (rfc1191) it need to know this MTU value for the ICMP packet. Patch change lookup and result struct bpf_fib_lookup, to contain this MTU value as output via a union with 'tot_len' as this is the value used for the MTU lookup. V5: - Fixed uninit value spotted by Dan Carpenter. - Name struct output member mtu_result Reported-by: kernel test robot <lkp@intel.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> --- include/uapi/linux/bpf.h | 11 +++++++++-- net/core/filter.c | 22 +++++++++++++++------- tools/include/uapi/linux/bpf.h | 11 +++++++++-- 3 files changed, 33 insertions(+), 11 deletions(-)